Pith. sign in

Animal Identification with Independent Foreground and Background Modeling

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We propose a method that robustly exploits background and foreground in visual identification of individual animals. Experiments show that their automatic separation, made easy with methods like Segment Anything, together with independent foreground and background-related modeling, improves results. The two predictions are combined in a principled way, thanks to novel Per-Instance Temperature Scaling that helps the classifier to deal with appearance ambiguities in training and to produce calibrated outputs in the inference phase. For identity prediction from the background, we propose novel spatial and temporal models. On two problems, the relative error w.r.t. the baseline was reduced by 22.3% and 8.8%, respectively. For cases where objects appear in new locations, an example of background drift, accuracy doubles.

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Bringing the Context Back into Object Recognition, Robustly

cs.CV · 2024-11-24 · conditional · novelty 6.0

Localizing the foreground before classification and fusing its classifier output with the full-image prediction improves accuracy and robustness to background shifts in supervised and zero-shot VLM recognition.

citing papers explorer

Showing 1 of 1 citing paper.

  • Bringing the Context Back into Object Recognition, Robustly cs.CV · 2024-11-24 · conditional · none · ref 39 · internal anchor

    Localizing the foreground before classification and fusing its classifier output with the full-image prediction improves accuracy and robustness to background shifts in supervised and zero-shot VLM recognition.